Yiqiao Zhang

Chenghanyu Zhang, Zekun Li, Peipei Li et al.

With the increasing integration of Multimodal Large Language Models (MLLMs) into the medical field, comprehensive evaluation of their performance in various medical domains becomes critical. However, existing benchmarks primarily assess general medical tasks, inadequately capturing performance in nuanced areas like the spine, which relies heavily on visual input. To address this, we introduce SpineBench, a comprehensive Visual Question Answering (VQA) benchmark designed for fine-grained analysis and evaluation of MLLMs in the spinal domain. SpineBench comprises 64,878 QA pairs from 40,263 spine images, covering 11 spinal diseases through two critical clinical tasks: spinal disease diagnosis and spinal lesion localization, both in multiple-choice format. SpineBench is built by integrating and standardizing image-label pairs from open-source spinal disease datasets, and samples challenging hard negative options for each VQA pair based on visual similarity (similar but not the same disease), simulating real-world challenging scenarios. We evaluate 12 leading MLLMs on SpineBench. The results reveal that these models exhibit poor performance in spinal tasks, highlighting limitations of current MLLM in the spine domain and guiding future improvements in spinal medicine applications. SpineBench is publicly available at https://zhangchenghanyu.github.io/SpineBench.github.io/.

Zenghui Chang, Yiqiao Zhang, Hong Cai Chen

Graph similarity learning, crucial for tasks such as graph classification and similarity search, focuses on measuring the similarity between two graph-structured entities. The core challenge in this field is effectively managing the interactions between graphs. Traditional methods often entail separate, redundant computations for each graph pair, leading to unnecessary complexity. This paper revolutionizes the approach by introducing a parallel graph interaction method called graph fusion. By merging the node sequences of graph pairs into a single large graph, our method leverages a global attention mechanism to facilitate interaction computations and to harvest cross-graph insights. We further assess the similarity between graph pairs at two distinct levels-graph-level and node-level-introducing two innovative, yet straightforward, similarity computation algorithms. Extensive testing across five public datasets shows that our model not only outperforms leading baseline models in graph-to-graph classification and regression tasks but also sets a new benchmark for performance and efficiency. The code for this paper is open-source and available at https://github.com/LLiRarry/GFM-code.git